© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19823
    Prev
    Next
    INDEX
    Explanations

    adverbs expressing movement or change over time

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    151
    +0.10
    0.5%
    106
    +0.10
    0.4%
    516
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.10
    0.03
    106
    +0.10
    0.02
    646
    +0.10
    0.02
    Negative Logits
    ãĥ¤
    -0.86
    ilion
    -0.85
    tein
    -0.81
    quickShipAvailable
    -0.74
     Parables
    -0.74
     IMAGES
    -0.71
    rito
    -0.70
    sports
    -0.70
    lua
    -0.70
    blance
    -0.69
    POSITIVE LOGITS
     phased
    1.00
     transitioning
    0.91
     encro
    0.90
     decreasing
    0.90
     trickle
    0.88
     progressing
    0.88
     creeping
    0.88
     drifting
    0.87
     increasing
    0.87
    escal
    0.85
    Activations Density 0.041%

    No Known Activations